Road marking recognition apparatus and method

• US 8,184,859 B2
• Filed: 11/30/2005
• Issued: 05/22/2012
• Est. Priority Date: 08/18/2005
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Tanji, Jou
• Primary Examiner(s): Le, Brian Q
• Assistant Examiner(s): BROOKS, JULIAN D
• Application Number:
  US11/289,502
• Publication Number:
  US 20070041614A1
• Time in Patent Office: 2,365 Days
• Field of Search: 382/103, 382/104, 382/209, 382/181, 701/28, 701/300, 701/301
• US Class Current: 382/104
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

An object of this invention is to provide a technique to correctly recognize road markings by a simple processing. This road marking recognition method: obtaining image data of a road, and storing the image data into an image data storage; detecting a first road marking in the image data stored in the image data storage, and storing position data of the first road marking into a storage; detecting a second road marking in the image data stored in the image data storage, and storing position data of the second road marking into a storage; judging based on the position data stored in the storage, whether or not a predefined proper mutual positional relationship between the first and second road markings is established; and evaluating a confidence degree for the detection result of the first and second road markings by using a result of the judging. For example, in a case of the road markings such as a crosswalk and a stop line, the stop line and the crosswalk have to be arranged in this order when viewing from the vehicle. Such a positional relationship is confirmed to evaluate the confidence degree.

Claims

1. A road marking recognition apparatus, comprising:

an image data storage device;

a unit that obtains image data of a road and stores said image data into said image data storage device;

a road marking data storage device; and

a road marking processor, and

wherein said road marking processor detects a stop line within a traffic lane delimited by white lines in said image data stored in said image data storage device, and stores position data of said stop line into said road marking data storage device, and further detects a crosswalk within said traffic lane delimited by said white lines in said image data stored in said image data storage device and stores position data of said crosswalk into said road marking data storage device, and

said road marking processor judges based on said position data stored in said road marking data storage device, whether or not the crosswalk appears after the stop line in a vehicle-traveling direction on said image data, and evaluates a confidence degree for detection results of the stop line and the crosswalk by using a judgment result of whether or not the crosswalk appears after the stop line in the vehicle-traveling direction.

2. The road marking recognition apparatus as set forth in claim 1, wherein said road marking processor comprises:

a unit to calculate a virtual position of said crosswalk from vehicle speed data and past position data stored in said road marking data storage device; and

a unit to calculate said confidence degree for said crosswalk from current position data stored in said road marking data storage device and said virtual position data.

3. The road marking recognition apparatus as set forth in claim 1, wherein said road marking processor comprises:

a unit to calculate a virtual position of said stop line from vehicle speed data and past position data stored in said road marking data storage device, and to evaluate said confidence degree for said stop line from current position data stored in said road marking data storage device and said virtual position data.

4. The road marking recognition apparatus as set forth in claim 1, further comprising:

a white line processor to recognize a white line delimiting traffic lanes in said image data stored in said image data storage, and stores position data of the recognized white line into a white lane data storage device, and limits a processing region of said image data based on said position data of said white line, which is stored in said white lane data storage device.

5. The road marking recognition apparatus as set forth in claim 4, wherein said white line processor comprises a unit to evaluate a confidence degree for said white line from said position data of the past recognized white line and current position data of said white line, which are stored in said white lane data storage device.

6. A computer-implemented road marking recognition method, comprising:

obtaining image data of a road;

storing said image data into an image data storage;

detecting a crosswalk within a traffic lane delimited by white lines in said image data stored in said image data storage;

storing position data of said crosswalk into a storage;

detecting a stop line within said traffic lane delimited by said white lines in said image data stored in said image data storage;

storing position data of said stop line into said storage;

judging based on said position data stored in said storage, whether or not the crosswalk appears after the stop line in a vehicle-traveling direction on said image data; and

evaluating a confidence degree for detection results of said crosswalk and said stop line by using a result of said judging.

7. The computer-implemented road marking recognition method as set forth in claim 6, wherein said detecting said crosswalk comprises:

calculating a virtual position of said crosswalk from vehicle speed data and the past position data stored in said storage; and

evaluating said confidence degree for said crosswalk from the current position data and said virtual position data, which are stored in said storage.

8. The computer-implemented road marking recognition method as set forth in claim 6, wherein said detecting said stop line comprises:

calculating a virtual position of said stop line from vehicle speed data and the past position data stored in said storage; and

evaluating said confidence degree for said stop line from the current position data and said virtual position data, which are stored in said storage.

9. The computer-implemented road marking recognition method as set forth in claim 6, further comprising:

recognizing a white line delimiting traffic lanes in said image data stored in said image data storage, and storing position data of the recognized white line into said storage; and

limiting a processing region of said image data based on said position data of said white line, which is stored in said storage.

10. The computer-implemented road marking recognition method as set forth in claim 9, wherein said recognizing comprises evaluating a confidence degree for said white line from said position data of the past recognized white line and the current position data of said white line, which are stored in said storage.

11. A non-transitory computer-readable storage medium storing a road marking recognition program, which when executed by a computer, causes the computer to execute a process, comprising:

obtaining image data of a road;

storing said image data into an image data storage;

detecting a crosswalk within a traffic lane delimited by white lines in said image data stored in said image data storage;

storing position data of said crosswalk into a storage;

detecting a stop line within said traffic lane delimited by said white lines in said image data stored in said image data storage;

storing position data of said stop line into said storage;

judging based on said position data stored in said storage, whether or not said crosswalk appears after the stop line in a vehicle-traveling direction on said image data; and

evaluating a confidence degree for detection results of said crosswalk and said stop line by using a result of said judging.

12. The non-transitory computer-readable storage medium as set forth in claim 11, wherein said detecting said crosswalk comprises:

calculating a virtual position of said crosswalk from vehicle speed data and the past position data stored in said storage; and

evaluating said confidence degree for said crosswalk from the current position data and said virtual position data, which are stored in said storage.

13. The non-transitory computer-readable storage medium as set forth in claim 11, wherein said detecting said stop line comprises:

calculating a virtual position of said stop line from vehicle speed data and the past position data stored in said storage; and

evaluating said confidence degree for said stop line from the current position data and said virtual position data, which are stored in said storage.

14. The non-transitory computer-readable storage medium as set forth in claim 11, further comprising:

recognizing a white line delimiting traffic lanes in said image data stored in said image data storage, and storing position data of the recognized white line into said storage; and

limiting a processing region of said image data based on said position data of said white line, which is stored in said storage.

15. The non-transitory computer-readable storage medium as set forth in claim 14, wherein said recognizing comprises evaluating a confidence degree for said white line from said position data of the past recognized white line and the current position data of said white line, which are stored in said storage.